Next Article in Journal
Land Subsidence in Chiayi, Taiwan, from Compaction Well, Leveling and ALOS/PALSAR: Aquaculture-Induced Relative Sea Level Rise
Next Article in Special Issue
Tree Death Not Resulting in Gap Creation: An Investigation of Canopy Dynamics of Northern Temperate Deciduous Forests
Previous Article in Journal
Quantification of Two-Dimensional Wave Breaking Dissipation in the Surf Zone from Remote Sensing Data
Previous Article in Special Issue
Assessment of Errors Caused by Forest Vegetation Structure in Airborne LiDAR-Derived DTMs
Article

Bayesian and Classical Machine Learning Methods: A Comparison for Tree Species Classification with LiDAR Waveform Signatures

1
LiDAR Applications for the Study of Ecosystems with Remote Sensing (LASERS) Laboratory, Department of Ecosystem Science and Management, Texas A&M University, College Station, TX 77843, USA
2
Department of Ecosystem Science and Management, Texas A&M University, College Station, TX 77843, USA
3
Department of Forest Engineering, Resources and Management, Oregon State University, Corvallis, OR 97331, USA
4
Institute of Psychology, University of Münster, Münster 48149, Germany
*
Author to whom correspondence should be addressed.
Remote Sens. 2018, 10(1), 39; https://doi.org/10.3390/rs10010039
Received: 16 November 2017 / Revised: 22 December 2017 / Accepted: 23 December 2017 / Published: 26 December 2017
(This article belongs to the Special Issue Lidar for Forest Science and Management)
A plethora of information contained in full-waveform (FW) Light Detection and Ranging (LiDAR) data offers prospects for characterizing vegetation structures. This study aims to investigate the capacity of FW LiDAR data alone for tree species identification through the integration of waveform metrics with machine learning methods and Bayesian inference. Specifically, we first conducted automatic tree segmentation based on the waveform-based canopy height model (CHM) using three approaches including TreeVaW, watershed algorithms and the combination of TreeVaW and watershed (TW) algorithms. Subsequently, the Random forests (RF) and Conditional inference forests (CF) models were employed to identify important tree-level waveform metrics derived from three distinct sources, such as raw waveforms, composite waveforms, the waveform-based point cloud and the combined variables from these three sources. Further, we discriminated tree (gray pine, blue oak, interior live oak) and shrub species through the RF, CF and Bayesian multinomial logistic regression (BMLR) using important waveform metrics identified in this study. Results of the tree segmentation demonstrated that the TW algorithms outperformed other algorithms for delineating individual tree crowns. The CF model overcomes waveform metrics selection bias caused by the RF model which favors correlated metrics and enhances the accuracy of subsequent classification. We also found that composite waveforms are more informative than raw waveforms and waveform-based point cloud for characterizing tree species in our study area. Both classical machine learning methods (the RF and CF) and the BMLR generated satisfactory average overall accuracy (74% for the RF, 77% for the CF and 81% for the BMLR) and the BMLR slightly outperformed the other two methods. However, these three methods suffered from low individual classification accuracy for the blue oak which is prone to being misclassified as the interior live oak due to the similar characteristics of blue oak and interior live oak. Uncertainty estimates from the BMLR method compensate for this downside by providing classification results in a probabilistic sense and rendering users with more confidence in interpreting and applying classification results to real-world tasks such as forest inventory. Overall, this study recommends the CF method for feature selection and suggests that BMLR could be a superior alternative to classical machining learning methods. View Full-Text
Keywords: Bayesian multinomial logistic regression; conditional inference forests; Random forests; waveform signatures; tree segmentation; watershed; composite waveform; decomposition Bayesian multinomial logistic regression; conditional inference forests; Random forests; waveform signatures; tree segmentation; watershed; composite waveform; decomposition
Show Figures

Figure 1

MDPI and ACS Style

Zhou, T.; Popescu, S.C.; Lawing, A.M.; Eriksson, M.; Strimbu, B.M.; Bürkner, P.C. Bayesian and Classical Machine Learning Methods: A Comparison for Tree Species Classification with LiDAR Waveform Signatures. Remote Sens. 2018, 10, 39. https://doi.org/10.3390/rs10010039

AMA Style

Zhou T, Popescu SC, Lawing AM, Eriksson M, Strimbu BM, Bürkner PC. Bayesian and Classical Machine Learning Methods: A Comparison for Tree Species Classification with LiDAR Waveform Signatures. Remote Sensing. 2018; 10(1):39. https://doi.org/10.3390/rs10010039

Chicago/Turabian Style

Zhou, Tan, Sorin C. Popescu, A. M. Lawing, Marian Eriksson, Bogdan M. Strimbu, and Paul C. Bürkner 2018. "Bayesian and Classical Machine Learning Methods: A Comparison for Tree Species Classification with LiDAR Waveform Signatures" Remote Sensing 10, no. 1: 39. https://doi.org/10.3390/rs10010039

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop